Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1840 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.7762. Min Act: -0.0000

Data Index: 863954 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1309674 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.6518. Min Act: -0.0000

Data Index: 401290 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1176531 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1288628 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1622999 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1615602 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1496612 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5677. Min Act: -0.0000

Data Index: 659310 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5887. Min Act: -0.0000

Data Index: 546217 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5271. Min Act: -0.0000

Data Index: 377672 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1099020 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1606092 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5519. Min Act: -0.0000

Data Index: 270280 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5313. Min Act: -0.0000

Data Index: 531354 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5397. Min Act: -0.0000

Data Index: 404337 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1603865 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1604830 (Python Code)

Max Activating Token Index: 715

Text #18

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1585786 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5286. Min Act: -0.0000

Data Index: 865160 (C4 (Web Text))

Max Activating Token Index: 122